Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    headings followed by descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ró
    0.44
     rutas
    0.41
     ruta
    0.41
     TY
    0.39
     користу
    0.39
    antu
    0.39
    iosas
    0.38
    "<<
    0.37
     jon
    0.37
    ",
    0.36
    POSITIVE LOGITS
    جهة
    0.39
    قیه
    0.39
     nghiệp
    0.38
     बैलेंस
    0.37
    ObjectTemp
    0.37
     relaxing
    0.36
    refundable
    0.35
    تباه
    0.35
     በጣም
    0.35
     phleg
    0.35
    Act Density 0.000%

    No Known Activations